Awesome

Applying temporal data mining to the Building Data Genome

This repository is a collection of temporal feature mining techniques implemented in the following publications:

Miller, C., & Meggers, F. (2017). Mining electrical meter data to predict principal building use, performance class, and operations strategy for hundreds of non-residential buildings. Energy and Buildings, 156(Supplement C), 360–373. https://doi.org/10.1016/j.enbuild.2017.09.056

Miller, Clayton. "What's in the box?! Towards explainable machine learning applied to non-residential building smart meter classification." Energy and Buildings 199 (2019): 523-536.

These notebooks use the Building Data Genome Project data set:

Miller, C., & Meggers, F. (2017). The Building Data Genome Project: An open, public data set from non-residential building electrical meters. Energy Procedia, 122, 439–444. https://doi.org/10.1016/j.egypro.2017.07.400

Using the notebooks

We recommend you download the Anaconda Python Distribution and use Jupyter to get an understanding of the data.

• Raw temporal and meta data are found in /data/raw/ in the Building Data Genome project and can be copied and pasted into the data folder in this project to begin

This project is based upon work completed part of Clayton Miller's Ph.D. dissertation: Miller, C., 2017. Screening Meter Data: Characterization of Temporal Energy Data from Large Groups of Non-Residential Buildings. ETH Zurich, Zurich, Switzerland.